© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9712
    Prev
    Next
    INDEX
    Explanations

    the word "out"

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Continuity
    -0.46
    følge
    -0.45
    wani
    -0.45
    )\}
    -0.44
    issors
    -0.44
    ρι
    -0.43
     Craig
    -0.43
    heizung
    -0.43
    férés
    -0.42
    prze
    -0.42
    POSITIVE LOGITS
    contentLoaded
    0.72
     CSM
    0.64
    Personensuche
    0.61
     Mahomet
    0.60
    setDo
    0.59
     getRule
    0.56
     profiling
    0.56
     SOT
    0.56
    WriteTagHelper
    0.55
     Soro
    0.53
    Activations Density 0.600%

    No Known Activations